antirez
@antirez
Reproducible bugs are candies.
I like programming too much for not liking automatic programming.
加入 May 2007
801 正在关注 81.4K 粉丝
Enjoy the DwarfStar glm-5.3-flash branch with GLM 5.3 Flash Q2 and Q4 support: single MacBook 128GB or DGX Spark inference, two MacBook RDMA 128GB each Q4 inference in tensor parallel fashion at 37 t/s single generation. ~500 t/s prefill for now, can be higher. ROCm soon.
显示更多
